Model comparison
Command R vs phi-3-medium 14B
Command R is the stronger model overall, scoring 31.0 to 29.1 on the Noometry Index.
Last verified . 3 shared benchmarks.
Cohere
MicrosoftSummary
- They share 3 benchmarks with published results for both. Command R scores higher in 2 categories and phi-3-medium 14B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R leads 30.5 to 9.1.
Side by side
| Command R | phi-3-medium 14B | |
|---|---|---|
| Provider | Cohere | Microsoft |
| Noometry Index | 31.0 | 29.1 |
| Released | 2024-08-30 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Command R: 28.8 (#301), phi-3-medium 14B: 36.3 (#198)
| Benchmark | Command R | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | 37.1% | 37.6% |
| BigCodeBench Complete | 45.2% | 48.7% |
| LiveBench Coding | 17.9% | — |
| LMArena Coding | 1170 | — |
Reasoning Not comparable
Command R: 13.3 (#329), phi-3-medium 14B: —
| Benchmark | Command R | phi-3-medium 14B |
|---|---|---|
| LiveBench Reasoning | 21.9% | — |
| LMArena Hard Prompts | 1164 | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.18 |
| HellaSwag | — | 82.4% |
| LiveBench | 27.5% | — |
| WinoGrande | — | 81.5% |
Math Too close to call
Command R: 25.8 (#244), phi-3-medium 14B: 25.2 (#249)
| Benchmark | Command R | phi-3-medium 14B |
|---|---|---|
| LiveBench Math | 19.4% | — |
| LMArena Math | 1155 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Command R leads
Command R: 30.5 (#219), phi-3-medium 14B: 9.1 (#301)
| Benchmark | Command R | phi-3-medium 14B |
|---|---|---|
| MMLU | 65.2% | 78% |
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1138 | — |
| ARC (AI2) Challenge | — | 91.6% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Command R: 35.9 (#240), phi-3-medium 14B: —
| Benchmark | Command R | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1174 | — |
| LMArena Chinese | 1182 | — |
| LMArena French | 1161 | — |
| LMArena German | 1176 | — |
| LMArena Japanese | 1143 | — |
| LMArena Korean | 1162 | — |
| LMArena Russian | 1174 | — |
| LMArena Spanish | 1150 | — |
Instruction Following Not comparable
Command R: 58.3 (#256), phi-3-medium 14B: —
| Benchmark | Command R | phi-3-medium 14B |
|---|---|---|
| LiveBench Instruction Following | 55.6% | — |
| LMArena Instruction Following | 1167 | — |
Long Context Not comparable
Command R: 36.3 (#226), phi-3-medium 14B: —
| Benchmark | Command R | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1198 | — |
Writing & Preference Not comparable
Command R: 38.4 (#248), phi-3-medium 14B: —
| Benchmark | Command R | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1187 | — |
| LMArena Creative Writing | 1170 | — |
| LMArena Multi-Turn | 1163 | — |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than phi-3-medium 14B?
Command R is the stronger model overall, scoring 31.0 to 29.1 on the Noometry Index.
Is Command R or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.3 versus 28.8 in the Noometry coding category.
How many benchmarks do Command R and phi-3-medium 14B share?
3 benchmarks have published results for both models. Command R has 29 scored results on Noometry and phi-3-medium 14B has 13.